Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Technology

    np_max-act · gemini-2.0-flash

    discussions about the potential benefits and risks of artificial intelligence for humanity.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     antigen
    -0.07
    unprocessable
    -0.06
     jiného
    -0.06
    .AreEqual
    -0.06
    歩
    -0.06
    DATE
    -0.06
     disparity
    -0.06
     advocate
    -0.06
    ontology
    -0.06
    info
    -0.06
    POSITIVE LOGITS
     altered
    0.07
    (mut
    0.07
    Official
    0.07
    मक
    0.06
    RAIN
    0.06
     Appeals
    0.06
    .answers
    0.06
     aprender
    0.06
     discovers
    0.06
     amused
    0.06
    Act Density 0.025%

    No Known Activations